Instructions to use SeonghoonYu/Masking-KD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SeonghoonYu/Masking-KD with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="SeonghoonYu/Masking-KD")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("SeonghoonYu/Masking-KD")
model = AutoModelForMultimodalLM.from_pretrained("SeonghoonYu/Masking-KD", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SeonghoonYu/Masking-KD with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SeonghoonYu/Masking-KD"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SeonghoonYu/Masking-KD",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/SeonghoonYu/Masking-KD

SGLang

How to use SeonghoonYu/Masking-KD with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SeonghoonYu/Masking-KD" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SeonghoonYu/Masking-KD",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SeonghoonYu/Masking-KD" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SeonghoonYu/Masking-KD",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use SeonghoonYu/Masking-KD with Docker Model Runner:
```
docker model run hf.co/SeonghoonYu/Masking-KD
```

Masking-KD / README.md

SeonghoonYu

Add paper link and citation

8f8ad2c verified 2 days ago

preview code

Raw History Blame Contribute Delete

2.7 kB

metadata

license: apache-2.0
base_model: Qwen/Qwen3-VL-2B-Thinking
datasets:
  - SeonghoonYu/Masking-KD-Rollouts
pipeline_tag: image-text-to-text
library_name: transformers
tags:
  - knowledge-distillation
  - multimodal-reasoning
  - qwen3_vl

Masking-KD (Qwen3-VL-2B-Thinking)

Checkpoint for Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation (NeurIPS 2026).

Qwen3-VL-2B-Thinking distilled from Qwen3-VL-8B-Thinking with Masking-KD.

Paper: https://arxiv.org/abs/2605.11651 | Code: https://github.com/Seonghoon-Yu/Masking-KD

Training


Student / Teacher	Qwen3-VL-2B-Thinking / Qwen3-VL-8B-Thinking
Data	SeonghoonYu/Masking-KD-Rollouts: 19,387 correct greedy teacher rollouts on ViRL39K
Schedule	2 epochs (76 steps), global batch size 512, learning rate 1e-6

Usage

The model was trained with the reasoning instruction below appended to each question.

from transformers import AutoModelForImageTextToText, AutoProcessor

model = AutoModelForImageTextToText.from_pretrained("SeonghoonYu/Masking-KD", dtype="auto", device_map="auto")
processor = AutoProcessor.from_pretrained("SeonghoonYu/Masking-KD")

question = "Find x."
instruction = (
    "You first think through the reasoning process as an internal monologue, enclosed within <think> </think> tags. "
    "Then, provide your final answer enclosed within \\boxed{}."
)
messages = [{
    "role": "user",
    "content": [
        {"type": "image", "image": "path/to/image.png"},
        {"type": "text", "text": f"{question}\n\n{instruction}"},
    ],
}]

inputs = processor.apply_chat_template(
    messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt"
).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=4096, do_sample=False)
print(processor.decode(outputs[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))

To reproduce the benchmark evaluation (Geo3K, MathVista, We-Math, MMK12, MathVerse, LogicVista, MMMU-Pro):

git clone https://github.com/Seonghoon-Yu/Masking-KD && cd Masking-KD
python evaluation/prepare_data.py
bash scripts/eval.sh SeonghoonYu/Masking-KD

Citation

@inproceedings{yu2026hide,
  title     = {Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation},
  author    = {Yu, Seonghoon and Nam, Dongjun and Lee, Byung-Kwan and Son, Jeany},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2026}
}